Triple

T16937486
Position Surface form Disambiguated ID Type / Status
Subject DTTA E410866 entity
Predicate servesAsHubFor P423 FINISHED
Object Tunisair E17920 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tunisair | Statement: [DTTA, servesAsHubFor, Tunisair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tunisair
Context triple: [DTTA, servesAsHubFor, Tunisair]
  • A. Tunisair chosen
    Tunisair is the flag carrier airline of Tunisia, operating domestic and international flights primarily from its hub in Tunis.
  • B. Air Sahara
    Air Sahara was an Indian private airline that operated domestic and limited international flights before being acquired and rebranded by Jet Airways.
  • C. Tassili Airlines
    Tassili Airlines is an Algerian airline based in Algiers that operates domestic and regional flights, primarily serving the oil and gas industry and general passenger traffic.
  • D. Libyan Arab Airlines
    Libyan Arab Airlines is the former national flag carrier of Libya, operating domestic and international passenger services primarily based out of Tripoli.
  • E. Royal Air Maroc
    Royal Air Maroc is the flag carrier airline of Morocco, operating an extensive network of flights across Africa, Europe, the Americas, and the Middle East from its main hub in Casablanca.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d886c886688190967be07322597ac9 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cf2adf448190ab0dbebb3addbd80 completed April 18, 2026, 6:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfe5210c8190873be6ccf2369b34 completed May 10, 2026, 6:35 p.m.
Created at: April 10, 2026, 5:30 a.m.